JMIR Publications

ABSTRACT

Despite increasing awareness about and advances in addressing social media misinformation, the free flow of false COVID-19 information has continued in recent months, affecting individuals’ preventive behaviors, including masking, testing, and vaccine uptake. In this paper, we describe our multidisciplinary efforts in health promotion, health communication, implementation science, deep learning, and social analytics to examine, model, and intervene on misinformation through social media datasets and interventions. We utilized qualitative, computational, and quantitative models to analyze multimodal datasets, including 16 semi-structured interviews, four community-based focus groups, and 432,562 COVID-19 social media posts. Our results reveal the complex intertwining of personal, cultural, and social influences of misinformation on individual behaviors and engagement. The linking of theoretical constructs underlying health behaviors to COVID-19 related social media interactions through semantic and syntactic features has revealed frequent interaction typologies in factual and misleading COVID-19 posts. This highlights the utility of large-scale social media datasets in enabling grassroots community interventions to thwart misinformation seeding and spread. Implications for consumer advocacy, data governance, and industry incentives are discussed for the sustainable role of social media solutions in public health.